Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3981 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1200. Min Act: -0.0001

Data Index: 1590769 (Python Code)

Max Activating Token Index: 647

Text #1

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1243. Min Act: -0.0001

Data Index: 1036408 (C4 (Web Text))

Max Activating Token Index: 752

Text #2

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1127. Min Act: -0.0001

Data Index: 1468418 (Python Code)

Max Activating Token Index: 717

Text #3

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1035. Min Act: -0.0001

Data Index: 1488261 (Python Code)

Max Activating Token Index: 402

Text #4

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1039. Min Act: -0.0001

Data Index: 1510626 (Python Code)

Max Activating Token Index: 61

Text #5

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0876. Min Act: -0.0001

Data Index: 1452661 (Python Code)

Max Activating Token Index: 776

Text #6

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0863. Min Act: -0.0001

Data Index: 1364639 (Python Code)

Max Activating Token Index: 281

Text #7

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0813. Min Act: -0.0001

Data Index: 1398223 (Python Code)

Max Activating Token Index: 38

Text #8

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0807. Min Act: -0.0001

Data Index: 1071914 (C4 (Web Text))

Max Activating Token Index: 5

Text #9

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0819. Min Act: -0.0001

Data Index: 1631445 (Python Code)

Max Activating Token Index: 741

Text #10

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0741. Min Act: -0.0001

Data Index: 1149495 (C4 (Web Text))

Max Activating Token Index: 714

Text #11

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0750. Min Act: -0.0001

Data Index: 1653655 (Python Code)

Max Activating Token Index: 579

Text #12

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0755. Min Act: -0.0001

Data Index: 1553552 (Python Code)

Max Activating Token Index: 815

Text #13

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0681. Min Act: -0.0001

Data Index: 321188 (C4 (Web Text))

Max Activating Token Index: 754

Text #14

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0743. Min Act: -0.0001

Data Index: 1334105 (C4 (Web Text))

Max Activating Token Index: 533

Text #15

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0733. Min Act: -0.0001

Data Index: 1588629 (Python Code)

Max Activating Token Index: 114

Text #16

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0693. Min Act: -0.0001

Data Index: 98516 (C4 (Web Text))

Max Activating Token Index: 502

Text #17

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0720. Min Act: -0.0001

Data Index: 895285 (C4 (Web Text))

Max Activating Token Index: 362

Text #18

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0713. Min Act: -0.0001

Data Index: 1423567 (Python Code)

Max Activating Token Index: 459

Text #19

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0627. Min Act: -0.0001

Data Index: 1517403 (Python Code)

Max Activating Token Index: 407